eeg artifact removal system for depression using a hybrid denoising approach

Introduction: several computer-aided diagnosis systems for depression are suggested for useby clinicians to authorize the diagnosis. eeg may be used as an objective analysis tool foridentifying depression in the initial stage to avoid it from reaching a severe and permanentstate. however, artifact contamination reduces the accuracy in eeg signal processing systems.methods: this work proposes a novel denoising method based on empirical mode decomposition(emd) ( with detrended fluctuation analysis (dfa) and wavelet packet transform. initially,real eeg recordings corresponding to depression patients are decomposed into various modefunctions by applying emd. then, dfa is used as the mode selection criteria. further waveletpackets decomposition (wpd)-based evaluation is applied to extract the cleaner signal.results: simulations were conducted on real eeg databases for depression to demonstrate theeffects of the proposed techniques. to conclude the efficacy of the proposed technique, snrand mae were identified. the obtained results indicated improved signal-to-noise ratio andlower values of mae for the combined emd-dfa-wpd technique. additionally, randomforest and svm (support vector machine)-based classification revealed the improvedaccuracy of 98.51% and 98.10% for the proposed denoising technique. whereas the accuracyof the emd- dfa is 98.01% and 95.81% and emd combined with dwt technique equaled98.0% and 97.21% for the emd- dfa technique for rf and svm, respectively, comparedto the proposed method. furthermore, the classification performance for both classifiers wascompared with and without denoising to highlight the effects of the proposed technique.conclusion: proposed denoising system results in better classification of depressed and healthyindividuals resulting in a better diagnosing system. these results can be further analyzed usingother approaches as a solution to the mode mixing problem of the emd approach.